Skip to main content
Project

AI Platforms for Accelerating 2D Materials Development

illustration showing data storage and a human brain sharing data for end use science
AI trained on LiST and multimodal synthesis data predicts transferable growth recipes, guides autonomous experiments in real time, and accelerates scalable 2D materials discovery for quantum devices. Credit: Sumner Harris (ORNL)

AI-Orchestrated Multimodal Platforms for Accelerated Discovery, Scale-Up, and Deployment of 2D Materials

The synthesis of 2D materials is highly sensitive to growth conditions, making it hard to achieve reproducible, transferable, and scalable processes — creating a persistent “valley of death” between lab discovery and manufacturable technologies. 

The project, “AI-Orchestrated Multimodal Platforms for Accelerated Discovery, Scale-Up, and Deployment of 2D Materials,” led by Pennsylvania State University, aims to transform thin-film synthesis of van der Waals chalcogenides — layered nanomaterials held together by weak intermolecular forces — using an AI-orchestrated multimodal platform. By integrating rich experimental data from Penn State’s 2DCC LiST database with in situ diagnostics and predictive simulations, the platform will autonomously guide synthesis, optimize growth recipes, and enable a scalable, transferable manufacturing process. This project is expected to accelerate the discovery of high-performance 2D materials and advance their deployment in next-generation microelectronics, optoelectronics, and quantum devices.